# Class Incremental Learning on ImageNet-100 (Base 0 Inc 5) 1.0 (test)

Source: [Class Incremental Learning on ImageNet-100 (Base 0 Inc 5) 1.0 (test)](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-100-base-0-inc-5-1-0-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-10T13:12:31.603Z

Evaluation of model performance on the test split of ImageNet-100 version 1.0 under a Class Incremental Learning setting configured for Base 0 and Increment 5, reporting Last and Average Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Class Incremental Learning |
| Dataset (including any stated split) | ImageNet-100 (Base 0 Inc 5) 1.0 (test) |
| Metric | Last Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Last Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-100-base-0-inc-5-1-0-test.md?metric=Last%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-100-base-0-inc-5-1-0-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Last Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GRACE | 64.86 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| DER | 64.62 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| MEMO | 56.02 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| FOSTER | 51.38 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| DGR | 48.68 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| ICARL | 44.48 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| REPLAY | 36.34 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| EWC | 5.6 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| FINETUNE | 4.66 | Not recorded | 69afa5bf2d603e6de3e43f2a |

### GRACE

Last Accuracy: 64.86. Result ID: 69b018a86dbb7075b95a2c91.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

Recorded evaluation configuration: {"#P":"134.04"}. This record does not assert independent reproduction.

### DER

Last Accuracy: 64.62. Result ID: 69b018a86dbb7075b95a2c8d.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699b1e209131cea23084.md>)

[Implementation](<https://github.com/Rhyssiyan/DER-ClassIL.pytorch>)

Recorded evaluation configuration: {"#P":"223.4"}. This record does not assert independent reproduction.

### MEMO

Last Accuracy: 56.02. Result ID: 69b018a86dbb7075b95a2c8f.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8c1e209131cea407e9.md>)

Recorded evaluation configuration: {"#P":"170.6"}. This record does not assert independent reproduction.

### FOSTER

Last Accuracy: 51.38. Result ID: 69b018a86dbb7075b95a2c8e.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d181e209131cea37af3.md>)

[Implementation](<https://github.com/G-U-N/ECCV22-FOSTER>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### DGR

Last Accuracy: 48.68. Result ID: 69b018a86dbb7075b95a2c90.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bb1e209131cea58382.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### ICARL

Last Accuracy: 44.48. Result ID: 69b018a86dbb7075b95a2c8c.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fded4.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### REPLAY

Last Accuracy: 36.34. Result ID: 69b018a86dbb7075b95a2c8a.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### EWC

Last Accuracy: 5.6. Result ID: 69b018a86dbb7075b95a2c8b.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### FINETUNE

Last Accuracy: 4.66. Result ID: 69b018a86dbb7075b95a2c89.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.